Related papers: Algorithmic Complexity Attacks on Dynamic Learned …

Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…

Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial…

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…

Predicting and enhancing inherent properties based on molecular structures is paramount to design tasks in medicine, materials science, and environmental management. Most of the current machine learning and deep learning approaches have…

Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples…

Active learning with strong and weak labelers considers a practical setting where we have access to both costly but accurate strong labelers and inaccurate but cheap predictions provided by weak labelers. We study this problem in the…

Most work on sequential learning assumes a fixed set of actions that are available all the time. However, in practice, actions can consist of picking subsets of readings from sensors that may break from time to time, road segments that can…

For sensitive problems, such as medical imaging or fraud detection, Neural Network (NN) adoption has been slow due to concerns about their reliability, leading to a number of algorithms for explaining their decisions. NNs have also been…

Federated learning (FL) emerged as a promising learning paradigm to enable a multitude of participants to construct a joint ML model without exposing their private training data. Existing FL designs have been shown to exhibit…

Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised increasing concerns. Existing research employs red teaming evaluations, utilizing multi-turn…

Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with…

State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models remains scarcely explored. Contrary to computer vision,…

Nowadays, we are witnessing an Artificial Intelligence revolution that dominates the technology landscape in various application domains, such as healthcare, robotics, automotive, security, and defense. Massive-scale AI models, which mimic…

The aggressive performance optimizations in modern microprocessors can result in security vulnerabilities. For example, timing-based attacks in processor caches can steal secret keys or break randomization. So far, finding cache-timing…

Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively…

Federated learning enables multiple clients to collaboratively contribute to the learning of a global model orchestrated by a central server. This learning scheme promotes clients' data privacy and requires reduced communication overheads.…

Large-scale load-altering attacks (LAAs) are known to severely disrupt power grid operations by manipulating several internet-of-things (IoT)-enabled load devices. In this work, we analyze power grid cascading failures induced by such…

While automated vehicles (AVs) are expected to revolutionize future transportation systems, emerging AV technologies open a door for malicious actors to compromise intelligent vehicles. As the first generation of AVs, adaptive cruise…

Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally lack the capability for continuous learning and self-evolution from interactions, limiting the…